def set_img(self, img):
"""
read an rgb image, set the gpu copy to be the lab image
"""
if img.shape[0] != self.dimy or img.shape[1] != self.dimx:
raise ValueError(img.shape, self.dimy, self.dimx)
if img.ndim == 1:
nChannels = 1
isNaN = np.isnan(img)
elif img.ndim == 3:
nChannels = 3
img_isNaN_r = np.isnan(img[:, :, 0])
img_isNaN_g = np.isnan(img[:, :, 1])
img_isNaN_b = np.isnan(img[:, :, 2])
isNaN = np.logical_or(img_isNaN_r, np.logical_or(img_isNaN_g, img_isNaN_b))
else:
raise NotImplementedError()
self.img = CpuGpuArray(arr=img)
self.img_isNaN = CpuGpuArray(arr=isNaN)
print('self.img', self.img)
print('self.img_isNaN', self.img_isNaN)
if nChannels == 3:
rgb_to_lab(img_gpu=self.img.gpu)
def get_init_seg(dimy, dimx, nPixels_in_square_side, use_hex):
"""
"""
M = nPixels_in_square_side
if use_hex:
s = create_string(dimx, dimy, nPixels_in_square_side)
# print(s)
fname = os.path.join(dirname_precomputed_hex_inits, s)
try:
FilesDirs.raise_if_file_does_not_exist(fname)
print("Loading", fname)
seg = np.load(fname)
return seg
except FileDoesNotExistError:
pass
msg = """
I could not find a precomputed (image-independent)
honeycomb initilization for this image size and this values of n.
So I will compute it from scratch and we will save the result in
{}
Next time you will run the code for an image of size
nRows={}, nCols={}, with n = {},
it will be faster.
""".format(fname, dimy, dimx, nPixels_in_square_side)
print(msg)
seg = CpuGpuArray.zeros((dimy, dimx), dtype=np.int32)
# length of each side
a = np.sqrt(M**2 / (1.5 * np.sqrt(3)))
H = a
W = np.sqrt(3) * H
# XX and YY need to be float
YY, XX = np.mgrid[0:float(dimy) + 0 * 1.5 * H:1.5 * H,
0:float(dimx) + 0 * W:W]
XX[::2] += float(W) / 2
centers = np.vstack([XX.ravel(), YY.ravel()]).T.copy()
centers = CpuGpuArray(centers)
honeycomb(seg.gpu, centers.gpu, seg.size)
seg.gpu2cpu()
np.save(fname, seg.cpu)
return seg.cpu
else:
seg_cpu = np.zeros((dimy, dimx), dtype=np.int32)
yy, xx = np.mgrid[:dimy, :dimx]
xx = xx.astype(np.float)
yy = yy.astype(np.float)
dimx = float(dimx)
dimy = float(dimy)
nTimesInX = np.floor(xx / M).max() + 1
seg_cpu = np.floor(yy / M) * nTimesInX + np.floor(xx / M)
seg_cpu = seg_cpu.astype(np.int32)
return seg_cpu
def calc_grad_alpha(self,
pa_space,
pat,
pts,
grad_alpha,
grad_per_point,
dt,
nTimeSteps,
nStepsODEsolver,
mysign=1,
transformed=None,
do_checks=True):
if transformed is None:
raise ValueError
if pts is transformed:
raise ValueError
if not isinstance(pts, CpuGpuArray):
raise TypeError
if not isinstance(transformed, CpuGpuArray):
raise TypeError
afs = pat.affine_flows
nC = pa_space.nC
nCs = pa_space.nCs
dim_domain = pa_space.dim_domain
dim_range = pa_space.dim_range
nHomoCoo = pa_space.nHomoCoo
if len(afs) != nC:
raise ValueError(len(afs), nC)
xmins = pa_space._xmins_LargeNumber
xmaxs = pa_space._xmaxs_LargeNumber
# BasMats=CpuGpuArray(pa_space.BasMats.reshape(pa_space.d,nC,-1))
BasMats = CpuGpuArray(pa_space.BasMats)
signed_sqAs = self.prepare_signedSqAs_for_gpu(pa_space, afs, nC,
nHomoCoo, mysign, dt)
d = pa_space.d
nPts = len(pts)
if d != len(BasMats):
raise ValueError
pa_space._gpu_calcs.calc_grad_alpha(xmins,
xmaxs,
signed_sqAs[:, :-1].reshape(
nC, -1).copy(),
BasMats,
pts,
dt,
nTimeSteps,
nStepsODEsolver,
pts_at_T=transformed,
grad_per_point=grad_per_point,
dim_domain=dim_domain,
dim_range=dim_range,
nCs=nCs.astype(np.int32),
incs=pa_space.incs)
return grad_per_point
def get_x_dense_with_both_endpoints(self, nPts):
"""
It seems the flow code has some bug with the endpoints.
So HBD.
"""
x = np.zeros([nPts, 1])
x[:, 0] = np.linspace(self.XMINS[0], self.XMAXS[0], nPts)
x = CpuGpuArray(x)
return x
def get_x_dense_with_the_last_point(self, nPts):
"""
TODO: it seems the flow code has some bug with the endpoints.
So I here I exclude the first point,
and pray that including the end point will be ok.
"""
x = np.zeros([nPts, 1])
x[:, 0] = np.linspace(self.XMINS[0], self.XMAXS[0], nPts + 1)[1:]
x = CpuGpuArray(x)
return x
def get_x_dense(self, nPts):
"""
TODO: it seems the flow code has some bug with the endpoints.
So for now I took them out.
Remark: surely I had some reason for this... the points are not between
0 and 1; rather, they are between XMINS[0] and self.XMAXS
"""
x = np.zeros([nPts, 1])
x[:, 0] = np.linspace(self.XMINS[0], self.XMAXS[0], nPts + 2)[1:-1]
x = CpuGpuArray(x)
return x
def set_data(self, x, y, range_start, range_end):
"""
For now, assumes dst was evaluated on evenly-space points
"""
if x.shape != y.shape:
raise ValueError(x.shape, y.shape)
if x.dtype != np.float64:
raise TypeError(x.dtype)
if y.dtype != np.float64:
raise TypeError(y.dtype)
nPts = len(x)
self.x = x
self.y = y
self.y_scale = range_end - range_start
self.y_offset = range_start
dst = (y - self.y_offset) / self.y_scale
if dst.ndim == 1:
dst = dst.reshape(nPts, 1).copy()
if not isinstance(dst, CpuGpuArray):
dst = CpuGpuArray(dst)
self.dst = dst
# cpa_space = self.tw.ms.L_cpa_space[0]
domain_start, domain_end = self.domain_start, self.domain_end
# self.interval = np.linspace(domain_start,domain_end,nPts)
# line = (x - domain_start) / ( domain_end - domain_start)
line = self.manipulate_predictors(x)
if line.ndim == 1:
line = line.reshape(nPts, 1).copy()
self.src = CpuGpuArray(line)
self.transformed = CpuGpuArray.zeros_like(self.src)
def set_img(self, img):
"""
read an rgb image, set the gpu copy to be the lab image
"""
if img.shape[0] != self.dimy or img.shape[1] != self.dimx:
raise ValueError(img.shape, self.dimy, self.dimx)
if img.ndim == 2:
nChannels = 1
elif img.ndim == 3:
nChannels = 3
else:
raise NotImplementedError(nChannels)
self.img = CpuGpuArray(arr=img.astype(np.float))
if nChannels == 3:
rgb_to_lab(img_gpu=self.img.gpu)
class Options(object):
axis_ij = False
gt = None
def __init__(self, name):
name = name.lower()
self.axis_ij = True
self.nCols = 250
self.nRows = 250
options = Options(name)
data.src = CpuGpuArray(data.src)
data.dst = CpuGpuArray(data.dst)
inference_params = InferenceParams()
# quick debug
#inference_params.MCMCniters_per_level=10
tf = TransformationFitter(
nRows=options.nRows,
nCols=options.nCols,
vol_preserve=inference_params.vol_preserve,
sigma_lm=inference_params.sigma_lm,
base=inference_params.base,
nLevels=inference_params.nLevels,
valid_outside=inference_params.valid_outside,
def __init__(self,
dimy,
dimx,
nPixels_in_square_side=None,
permute_seg=False,
s_std=20,
i_std=20,
prior_count=1,
calc_s_cov=True,
use_hex=False):
"""
arguments:
nPixels_in_square_side: number of the pixels on the side of a superpixels
permute_seg: only for display purpose, whether to permute the superpixels labling,
s_std: fixed as nPixels_on_side
i_std: control the relative importance between RGB and location.
The smaller it is, bigger the RGB effect is / more irregular the superpixels are.
prior_count: determines the weight of Inverse-Wishart prior of space covariance(ex:1,5,10)
calc_s_cov: whether or not to update the covariance of color component of Gaussians
use_hex: initialize the superpixels as hexagons or squares
"""
# init the field "nPixels_in_square_side"
if nPixels_in_square_side is None:
raise NotImplementedError
self.nPixels_in_square_side = nPixels_in_square_side
if not (3 < nPixels_in_square_side < min(dimx, dimy)):
msg = """
Expected
3<nPixels_in_square_side<min(dimx,dimy)={1}
but nPixels_in_square_side={0}
""".format(nPixels_in_square_side, min(dimx, dimy))
raise ValueError(msg)
self.dimx = dimx
self.dimy = dimy
self.nChannels = 3 # RGB/LAB
#init the field "seg"
self.use_hex = use_hex
self.permute_seg = permute_seg
seg = get_init_seg(dimy=dimy,
dimx=dimx,
nPixels_in_square_side=nPixels_in_square_side,
use_hex=use_hex)
if permute_seg:
seg = random_permute_seg(seg)
self.seg = CpuGpuArray(arr=seg)
# keep the initial segmentation for use in images of the same size
# so that we won't re-calculate the initial segmenation
self.seg_ini = self.seg.cpu.copy()
#init the field nSuperpixels
self.nSuperpixels = self.seg.cpu.max() + 1
if self.nSuperpixels <= 1:
raise ValueError(self.nSuperpixels)
#init the field "superpixels"
self.superpixels = Superpixels(self.nSuperpixels,
s_std=s_std,
i_std=i_std,
prior_count=prior_count,
nChannels=self.nChannels)
#init the field "border"(bool array, true for pixels on the superpixel boundary)
border = gpuarray.zeros((dimy, dimx), dtype=np.bool)
self.border = CpuGpuArray(arr=border)
find_border_pixels(seg_gpu=self.seg.gpu, border_gpu=self.border.gpu)
self.border.gpu2cpu()
self.border_ini = self.border.cpu.copy()
print('dimy,dimx=', dimy, dimx)
print('nSuperpixels =', self.nSuperpixels)
# pts_grid = pts_grid[:,5:-5,5:-5,5:-5]
pts=np.vstack([pts_grid[0].ravel(),
pts_grid[1].ravel(),
pts_grid[2].ravel()]).T.copy()
if 0:
ds0,ds1,ds2=10,10,10
# pts_grid=cpa_space.x_dense_grid[:,::ds0,::ds1,50:51]
pts_grid=cpa_space.x_dense_grid[:,::ds0,::ds1,::ds2]
pts=np.vstack([pts_grid[0].ravel(),
pts_grid[1].ravel(),
pts_grid[2].ravel()]).T.copy()
pts = CpuGpuArray(pts)
print pts_grid.shape
print pts.shape
pts_transformed = CpuGpuArray.zeros_like(pts)
mu = cpa_space.get_zeros_theta()
np.random.seed(0)
# theta *= 4
#
def disp_deformed_grid_lines(self, level, color=None, lw=1):
# return
if self.hlines is None or self.vlines is None:
raise ValueError
hlines, vlines = self.hlines, self.vlines
# for lines,c in zip([hlines,vlines],['r','b']):
# pts_at_0=np.asarray([lines[:,0,:].flatten(),
# lines[:,1,:].flatten()]).T
# pts_at_0 = CpuGpuArray(pts_at_0.copy())
# pts_at_T=CpuGpuArray.zeros_like(pts_at_0)
# self.calc_T_fwd(pts_src=pts_at_0,
# pts_fwd=pts_at_T,
# level=level,verbose=0,int_quality=1)
# if self.nCols != self.nCols:
# raise NotImplementedError
# pts_at_T.gpu2cpu()
# lines_new_x=pts_at_T.cpu[:,0].reshape(lines[:,0,:].shape).copy()
# lines_new_y=pts_at_T.cpu[:,1].reshape(lines[:,0,:].shape).copy()
# for line_new_x,line_new_y in zip(lines_new_x,lines_new_y):
#
# plt.plot(line_new_x,line_new_y,c)
if color is None:
colors = ['r', 'b']
else:
colors = [color, color]
s = hlines.shape
if s[2] <= 1:
raise ValueError
p = 0
L = 50000
if L >= s[2]:
while p < np.ceil(s[2]):
hlines = self.hlines[:, :, p:p + L]
vlines = self.vlines[:, :, p:p + L]
p += L
for lines, c in zip([hlines, vlines], colors):
pts_at_0 = np.asarray(
[lines[:, 0, :].flatten(), lines[:, 1, :].flatten()]).T
if pts_at_0.size == 0:
break
pts_at_0 = CpuGpuArray(pts_at_0.copy())
pts_at_T = CpuGpuArray.zeros_like(pts_at_0)
self.calc_T_fwd(pts_src=pts_at_0,
pts_fwd=pts_at_T,
level=level,
int_quality=1)
if self.nCols != self.nCols:
raise NotImplementedError
pts_at_T.gpu2cpu()
lines_new_x = pts_at_T.cpu[:, 0].reshape(
lines[:, 0, :].shape).copy()
lines_new_y = pts_at_T.cpu[:, 1].reshape(
lines[:, 0, :].shape).copy()
for line_new_x, line_new_y in zip(lines_new_x,
lines_new_y):
plt.plot(line_new_x, line_new_y, c, lw=lw)
else:
raise NotImplementedError
def disp_orig_grid_lines(self, level, color=None, lw=1):
# return
try:
self.hlines
self.vlines
except AttributeError:
raise Exception("You need to call create_grid_lines first")
if self.hlines is None:
raise ValueError
if self.vlines is None:
self.vlines = self.hlines
hlines, vlines = self.hlines, self.vlines
s = hlines.shape
if s[2] <= 1:
raise ValueError
p = 0
L = 50000
if color is None:
colors = ['r', 'b']
else:
colors = [color, color]
if L >= s[2]:
while p < np.ceil(s[2]):
hlines = self.hlines[:, :, p:p + L]
vlines = self.vlines[:, :, p:p + L]
p += L - 1
for lines, c in zip([hlines, vlines], colors):
pts_at_0 = np.asarray(
[lines[:, 0, :].flatten(), lines[:, 1, :].flatten()]).T
if pts_at_0.size == 0:
break
# print _pts_at_0.shape
pts_at_0 = CpuGpuArray(pts_at_0.copy())
if self.nCols != self.nCols:
raise NotImplementedError
pts_at_0.gpu2cpu()
lines_new_x = pts_at_0.cpu[:, 0].reshape(
lines[:, 0, :].shape).copy()
lines_new_y = pts_at_0.cpu[:, 1].reshape(
lines[:, 0, :].shape).copy()
for line_new_x, line_new_y in zip(lines_new_x,
lines_new_y):
plt.plot(line_new_x, line_new_y, c, lw=lw)
else:
hlines = self.hlines
vlines = self.vlines
for lines, c in zip([hlines, vlines], colors):
pts_at_0 = np.asarray(
[lines[:, 0, :].flatten(), lines[:, 1, :].flatten()]).T
if pts_at_0.size == 0:
break
# print _pts_at_0.shape
pts_at_0 = CpuGpuArray(pts_at_0.copy())
if self.nCols != self.nCols:
raise NotImplementedError
pts_at_0.gpu2cpu()
lines_new_x = pts_at_0.cpu[:, 0].reshape(
lines[:, 0, :].shape).copy()
lines_new_y = pts_at_0.cpu[:, 1].reshape(
lines[:, 0, :].shape).copy()
for line_new_x, line_new_y in zip(lines_new_x, lines_new_y):
plt.plot(line_new_x, line_new_y, c, lw=lw)
def example(tess='I',
base=[2, 2, 2],
nLevels=1,
zero_v_across_bdry=[True] * 3,
vol_preserve=False,
nRows=100,
nCols=100,
nSlices=100,
use_mayavi=False,
eval_v=False,
eval_cell_idx=False):
tw = TransformWrapper(nRows=nRows,
nCols=nCols,
nSlices=nSlices,
nLevels=nLevels,
base=base,
zero_v_across_bdry=zero_v_across_bdry,
tess=tess,
valid_outside=False,
only_local=False,
vol_preserve=vol_preserve)
print_iterable(tw.ms.L_cpa_space)
print tw
# create some fake 3D image.
img = np.zeros((nCols, nRows, nSlices), dtype=np.float64)
# img[:]=np.random.random_integers(0,255,img.shape)
# Fill the image with the x coordinates as fake values
img[:] = tw.pts_src_dense.cpu[:, 0].reshape(img.shape)
img0 = CpuGpuArray(img.copy().astype(np.float64))
img_wrapped_fwd = CpuGpuArray.zeros_like(img0)
img_wrapped_inv = CpuGpuArray.zeros_like(img0)
seed = 0
np.random.seed(seed)
ms_Avees = tw.get_zeros_PA_all_levels()
ms_theta = tw.get_zeros_theta_all_levels()
if tess == 'II':
for level in range(tw.ms.nLevels):
cpa_space = tw.ms.L_cpa_space[level]
Avees = ms_Avees[level]
# 1/0
if level == 0:
tw.sample_gaussian(level,
ms_Avees[level],
ms_theta[level],
mu=None) # zero mean
# ms_theta[level].fill(0)
# ms_theta[level][-4]=10
cpa_space.theta2Avees(theta=ms_theta[level], Avees=Avees)
else:
tw.sample_from_the_ms_prior_coarse2fine_one_level(
ms_Avees, ms_theta, level_fine=level)
else:
# For tess='I' in 3D, I have yet to implement the coarse-to-fine sampling.
for level in range(tw.ms.nLevels):
cpa_space = tw.ms.L_cpa_space[level]
velTess = cpa_space.zeros_velTess()
ms_Avees[level].fill(0)
Avees = ms_Avees[level]
tw.sample_gaussian_velTess(level, Avees, velTess, mu=None)
print 'img shape:', img0.shape
# You don't have use these. You can use any 2d array
# that has 3 columns (regardless of the number of rows).
pts_src = tw.pts_src_dense
pts_src = CpuGpuArray(pts_src.cpu[::1].copy())
# Create a buffer for the output
pts_fwd = CpuGpuArray.zeros_like(pts_src)
pts_inv = CpuGpuArray.zeros_like(pts_src)
for level in range(tw.ms.nLevels):
tw.update_pat_from_Avees(ms_Avees[level], level)
if eval_v:
# Evaluating the velocity field.
# You don't have to do it in unless you want to visualize v.
# (when evaluting the treansformation, v will be internally
# evaluated anyway -- but its result won't be stored)
tw.calc_v(level=level)
print 'level', level
print
print 'number of points:', len(pts_src)
print 'number of cells:', tw.ms.L_cpa_space[level].nC
# optional, if you want to time it
timer_gpu_T_fwd = GpuTimer()
# Simply calling
# tic = time.clock()
# and then
# tic = time.clock()
# won't work.
# In fact, most likely you will get that toc-tic is zero.
# You need to use the GpuTimer object. When you do that,
# one side effect is that suddenly the toc-tic from above will
# give you a more realistic result.
tic = time.clock()
timer_gpu_T_fwd.tic()
tw.calc_T_fwd(pts_src, pts_fwd, level=level)
timer_gpu_T_fwd.toc()
toc = time.clock()
print 'Time, in sec, for computing T_fwd:'
print timer_gpu_T_fwd.secs
print toc - tic # likely to be 0, unless you also used the GpuTimer.
# You can also time the inv of course. Results will be similar.
tw.calc_T_inv(pts_src, pts_inv, level=level)
if eval_cell_idx:
# cell_idx is computed here just for display.
cell_idx = CpuGpuArray.zeros(len(pts_src), dtype=np.int32)
tw.calc_cell_idx(pts_src, cell_idx, level)
tw.remap_fwd(pts_inv, img0, img_wrapped_fwd)
tw.remap_inv(pts_fwd, img0, img_wrapped_inv)
# For display purposes, do gpu2cpu transfer
print "For display purposes, do gpu2cpu transfer"
if eval_cell_idx:
cell_idx.gpu2cpu()
if eval_v:
tw.v_dense.gpu2cpu()
pts_fwd.gpu2cpu()
pts_inv.gpu2cpu()
img_wrapped_fwd.gpu2cpu()
img_wrapped_inv.gpu2cpu()
if use_mayavi:
ds = 1 # downsampling factor
i = 17
pts_src_grid = pts_src.cpu.reshape(tw.nRows, tw.nCols, -1, 3)
pts_src_ds = pts_src_grid[::ds, ::ds, i].reshape(-1, 3)
pts_fwd_grid = pts_fwd.cpu.reshape(tw.nRows, tw.nCols, -1, 3)
pts_fwd_ds = pts_fwd_grid[::ds, ::ds, i].reshape(-1, 3)
pts_inv_grid = pts_inv.cpu.reshape(tw.nRows, tw.nCols, -1, 3)
pts_inv_ds = pts_inv_grid[::ds, ::ds, i].reshape(-1, 3)
from of.my_mayavi import *
mayavi_mlab_close_all()
mayavi_mlab_figure_bgwhite('src')
x, y, z = pts_src_ds.T
mayavi_mlab_plot3d(x, y, z)
mayavi_mlab_figure_bgwhite('fwd')
x, y, z = pts_fwd_ds.T
mayavi_mlab_plot3d(x, y, z)
figsize = (12, 12)
plt.figure(figsize=figsize)
i = 17 # some slice
plt.subplot(131)
plt.imshow(img0.cpu[:, :, i].astype(np.uint8), interpolation="Nearest")
plt.title('slice from img')
plt.subplot(132)
plt.imshow(img_wrapped_fwd.cpu[:, :, i].astype(np.uint8),
interpolation="Nearest")
plt.axis('off')
plt.title('slice from fwd(img)')
plt.subplot(133)
plt.imshow(img_wrapped_inv.cpu[:, :, i].astype(np.uint8),
interpolation="Nearest")
plt.axis('off')
plt.title('slice from inv(img)')
if 0: # debug
cpa_space = tw.ms.L_cpa_space[level]
if eval_v:
vx = tw.v_dense.cpu[:, 0].reshape(
cpa_space.x_dense_grid_img.shape[1:])
vy = tw.v_dense.cpu[:, 1].reshape(
cpa_space.x_dense_grid_img.shape[1:])
vz = tw.v_dense.cpu[:, 2].reshape(
cpa_space.x_dense_grid_img.shape[1:])
plt.figure()
plt.imshow(vz[:, :, 17], interpolation="Nearest")
plt.colorbar()
plt.title('vz in some slice')
return tw
# if level !=ms.nLevels-1:
# continue
print 'level: ', level
print cpa_space
# cpa_calcs=CpaCalcs(Nx=Nx,Ny=Ny,use_GPU_if_possible=True)
# As = cpa_space.Avees2As(sample_Avees_all_levels[level])
# As[:,0,:]=0
# sample_Avees_all_levels[level] = cpa_space.As2Avees(As)
# sample_cpa_all_levels[level] = cpa_space.project(sample_Avees_all_levels[level])
# ipshell('hi')
# pat= PAT(pa_space=cpa_space,Avees=sample_Avees_all_levels[level])
cpa_space.update_pat(Avees=sample_Avees_all_levels[level])
pts = CpuGpuArray(cpa_space.x_dense_img)
v_dense = CpuGpuArray.zeros_like(pts)
cpa_space.calc_v(pts=pts, out=v_dense)
v_dense.gpu2cpu() # for display
plt.figure(level)
of.plt.maximize_figure()
scale = [.4, 0.25][cpa_space.vol_preserve]
scale = 1 * Nx * 30
scale = np.sqrt((v_dense.cpu**2).sum(axis=1)).mean() / 10
for h in [233, 236][:1]:
plt.subplot(h)
cpa_space.quiver(cpa_space.x_dense_grid_img,
_calc_ll_per_sample(ll, err, np.float64(sigma))
if __name__ == '__main__':
from pycuda import autoinit
from of.gpu import CpuGpuArray
import numpy as np
msg = """
The code below is for landmarks,
not signals"""
raise NotImplementedError(msg)
yy, xx = np.mgrid[-2:2:1, -2:2:1]
x = np.vstack([xx.ravel(), yy.ravel()]).T
del xx, yy
x = CpuGpuArray(x.copy().astype(np.float))
print x
y = np.random.standard_normal(x.shape)
y = CpuGpuArray(y)
err = CpuGpuArray.zeros_like(y)
nPts = len(err)
ll = CpuGpuArray.zeros(nPts)
calc_signal_err_per_sample(x.gpu, y.gpu, err.gpu)
sigma = 1.0
calc_ll_per_sample(ll.gpu, err.gpu, sigma)
err.gpu2cpu()
ll.gpu2cpu()
def calc_trajectory(self,
pa_space,
pat,
pts,
dt,
nTimeSteps,
nStepsODEsolver=100,
mysign=1):
"""
Returns: trajectories
trajectories.shape = (nTimeSteps,nPts,pa_space.dim_domain)
todo: make a more efficient use with CpuGpuArray
"""
if not isinstance(pts, CpuGpuArray):
raise ObsoleteError
nC = pa_space.nC
nCs = pa_space.nCs
nHomoCoo = pa_space.nHomoCoo
dim_domain = pa_space.dim_domain
dim_range = pa_space.dim_range
incs = pa_space.incs
if dim_domain != 2:
raise NotImplementedError
if pts.ndim != 2:
raise ValueError(pts.shape)
if pts.shape[1] != pa_space.dim_domain:
raise ValueError(pts.shape)
x, y = pts.cpu.T
x_old = x.copy()
y_old = y.copy()
nPts = x_old.size
history_x = np.zeros((nTimeSteps, nPts), dtype=self.my_dtype)
history_y = np.zeros_like(history_x)
history_x.fill(np.nan)
history_y.fill(np.nan)
afs = pat.affine_flows
signed_sqAs, Tlocals = self.prepare_signedSqAs_and_Tlocals_for_gpu(
pa_space, afs, nC, nHomoCoo, mysign, dt)
# As = mysign*np.asarray([c.A for c in afs]).astype(self.my_dtype)
# Trels = np.asarray([expm(dt*c.A*mysign) for c in afs ])
xmins = np.asarray([c.xmins for c in afs]).astype(self.my_dtype)
xmaxs = np.asarray([c.xmaxs for c in afs]).astype(self.my_dtype)
xmins[xmins <= self.XMINS] = -self._LargeNumber
xmaxs[xmaxs >= self.XMAXS] = +self._LargeNumber
if pa_space.has_GPU == False or self.use_GPU_if_possible == False:
Warning("Not using GPU!")
raise NotImplementedError
else:
pts_at_0 = np.zeros((nPts, pa_space.dim_domain))
pts_at_0[:, 0] = x_old.ravel()
pts_at_0[:, 1] = y_old.ravel()
trajectories = pa_space._gpu_calcs.calc_trajectory(
xmins,
xmaxs,
# Trels,As,
Tlocals[:, :-1].reshape(nC, -1).copy(),
signed_sqAs[:, :-1].reshape(nC, -1).copy(),
pts_at_0,
dt,
nTimeSteps,
nStepsODEsolver,
dim_domain,
dim_range,
nCs,
incs)
# add the starting points
trajectories = np.vstack([pts_at_0, trajectories])
# reshaping
trajectories = trajectories.reshape(1 + nTimeSteps, nPts,
pa_space.dim_domain)
trajectories = CpuGpuArray(trajectories)
return trajectories
if __name__ == '__main__':
from pycuda import autoinit
from of.gpu import CpuGpuArray
import numpy as np
# x = CpuGpuArray(np.arange(4).astype(np.float))
# y = CpuGpuArray(np.arange(4)[::-1].copy().astype(np.float))
#
# print x
# print y
#
# err_by_der = CpuGpuArray.zeros(3,dtype=x.dtype)
# calc_err_by_der_per_sample(x.gpu,y.gpu,err_by_der.gpu,0.01)
#
# print err_by_der
x = CpuGpuArray((np.arange(-3, 4)**2).astype(np.float))
print x
print 'sum diff'
print np.diff(x.cpu).sum()
print calc_sum_prime(x.gpu, np.int32(len(x)))
print 'sum ddiff'
print np.diff(x.cpu, n=2).sum()
print calc_sum_double_prime(x.gpu, np.int32(len(x)))
print 'sum abs(ddiff)'
print np.abs(np.diff(x.cpu, n=2)).sum()
print calc_sum_abs_double_prime(x.gpu, np.int32(len(x)))
# This needs to be evenly spaced.
interval = np.linspace(-3,3,x_dense.size)
# # There is actually a reason why I do the funny thing below
## x_select = x[::100/2].copy()
# x_select = x.copy()[::-1][::100/2][::-1]
#
#
# # but now that I need to copy, it may not be relevant any more...
# x_select = x_select.copy()
# x_select = x[::100/2].copy()
x_select = CpuGpuArray(x_dense.cpu[::100/2].copy())
# x_select[:]=np.linspace(.1,1.0,len(x_select))
# x_select[3:-1] +=.1
# x_select[6:-1] -=.05
# pat = PAT(pa_space=cpa_space,Avees=sample_Avees_all_levels[level])
cpa_space.update_pat(Avees=sample_Avees_all_levels[level])
#
v_dense = CpuGpuArray.zeros_like(x_dense)
cpa_space.calc_v(pts=x_dense,out=v_dense)
def __init__(
self,
nRows,
nCols,
vol_preserve=False,
nLevels=1,
base=[2, 2],
scale_spatial=1.0 * .1,
scale_value=100,
zero_v_across_bdry=[False] * 2, # For now, don't change that.
tess=None,
valid_outside=True,
only_local=False,
cont_constraints_are_separable=False):
"""
Input params:
nRows: number of rows in the image
nCols: number of cols in the image
vol_preserve: boolean flag (area-preserving or not)
nLevels: number of levels in the multiscale representation
base = (# of cells in X direction, # of cells in Y direction)
Determines the resolution of the tesselation as the base
level of the multiscale representation.
scale_spatial: paramter for the Gaussian prior. Higher val <=> more smoothness
scale_value: paramter for the Gaussian prior. Higher val <=> larger covariance
"""
super(type(self), self).__init__(
vol_preserve=vol_preserve,
nLevels=nLevels,
base=base,
scale_spatial=scale_spatial,
scale_value=scale_value,
zero_v_across_bdry=zero_v_across_bdry,
tess=tess,
valid_outside=valid_outside,
only_local=only_local,
cont_constraints_are_separable=cont_constraints_are_separable)
self.nRows = self.args.nRows = nRows
self.nCols = self.args.nCols = nCols
print self.args
# print
if tess == 'tri':
tess = 'I'
if tess == 'rect':
tess == 'II'
if tess not in ['I', 'II']:
raise ValueError(tess, "tess must be in ['I','II']")
if only_local and tess != 'I':
raise NotImplementedError
self.nRows = nRows
self.nCols = nCols
XMINS = [0, 0]
XMAXS = [nCols, nRows] # Note: This inclusive; e.g., if your image is
# 512x512, XMAXS=[512,512], not [511,511]
# XMINS=[-nCols/2,-nRows/2]
# XMAXS=[ nCols/2, nRows/2]
warp_around = [False, False] # For now, don't change that.
# zero_v_across_bdry=[False,False] # For now, don't change that.
Nx = XMAXS[0] - XMINS[0]
Ny = XMAXS[1] - XMINS[1]
self.config_plt = ConfigPlt(Nx=Nx, Ny=Ny)
Ngrids = [Nx, Ny]
ms = Multiscale(
XMINS,
XMAXS,
zero_v_across_bdry,
vol_preserve,
warp_around=warp_around,
nLevels=nLevels,
base=base,
tess=tess,
Ngrids=Ngrids,
valid_outside=valid_outside,
only_local=only_local,
cont_constraints_are_separable=cont_constraints_are_separable)
self.ms = ms
if only_local == False:
self.msp = MultiscaleCoarse2FinePrior(ms,
scale_spatial=scale_spatial,
scale_value=scale_value,
left_blk_std_dev=1.0 / 100,
right_vec_scale=1)
else:
self.msp = None
self.pts_src_dense = CpuGpuArray(ms.L_cpa_space[0].x_dense_img.copy())
self.v_dense = CpuGpuArray.zeros_like(self.pts_src_dense)
self.transformed_dense = CpuGpuArray.zeros_like(self.pts_src_dense)
self.params_flow_int = get_params_flow_int()
self.params_flow_int.nStepsODEsolver = 10 # Usually this is enough.
self.params_flow_int_coarse = copy.deepcopy(self.params_flow_int)
self.params_flow_int_coarse.nTimeSteps /= 10
self.params_flow_int_coarse.dt *= 10
self.params_flow_int_fine = copy.deepcopy(self.params_flow_int)
self.params_flow_int_fine.nTimeSteps *= 10
self.params_flow_int_fine.dt /= 10
self.ms_pats = ms.pats
def __init__(self, nSuperpixels, s_std, i_std, prior_count, nChannels):
"""
Initilize the parameters for the superpixels:
The means are set to zeros at this point,
and will be set later in the first M step.
The space/color covariances (and their inverse), however, are being set
to initial values here.
We use a Inverse-Wishart prior on the space covariance
Arguments:
nSuperpixels: the number of superpixels to generate
s_std: should be fixed as nPixels_on_side
i_std: control the relative importance between RGB and location.
The smaller it is, bigger the RGB effect is / more irregular the superpixels are.
prior_count: determines the weight of Inverse-Wishart prior of space covariance(ex:1,5,10)
nChannels: the number of channels of the input image (gray:1, LAB/RGB: 3)
"""
if nChannels not in (1,3):
raise NotImplementedError(nChannels)
dim_i=nChannels
dim_s=2
self.dim_i=dim_i
self.dim_s=dim_s
self.nSuperpixels=nSuperpixels
self.s_std, self.i_std, self.prior_count = s_std,i_std,prior_count
mu_s = CpuGpuArray.zeros((nSuperpixels,dim_s))
mu_i = CpuGpuArray.zeros((nSuperpixels,dim_i))
Sigma_s = CpuGpuArray.zeros(shape = (nSuperpixels,dim_s,dim_s))
J_s = CpuGpuArray.zeros_like(Sigma_s)
Sigma_i = CpuGpuArray.zeros((nSuperpixels,dim_i,dim_i))
J_i = CpuGpuArray.zeros_like(Sigma_i)
logdet_Sigma_i = CpuGpuArray.zeros((nSuperpixels,1)) # scalars
logdet_Sigma_s = CpuGpuArray.zeros((nSuperpixels,1))
# start with unnormalized counts (uniform)
counts = np.ones(nSuperpixels,dtype=np.int32)
counts = CpuGpuArray(counts)
self.params = Bunch()
self.params.mu_i = mu_i
self.params.mu_s = mu_s
self.params.Sigma_i = Sigma_i
self.params.Sigma_s = Sigma_s
self.params.prior_sigma_s_sum = Sigma_s
self.params.J_i = J_i
self.params.J_s = J_s
self.params.logdet_Sigma_i = logdet_Sigma_i
self.params.logdet_Sigma_s = logdet_Sigma_s
self.params.counts = counts
# set those parameters related to covariance
self.initialize_params()
# intermediate arrays needed for the Gaussian parameter calculation on GPU
self.gpu_helper = Bunch()
self.gpu_helper.mu_i_helper = gpuarray.zeros((nSuperpixels,dim_i),dtype=np.int32)
self.gpu_helper.mu_s_helper = gpuarray.zeros((nSuperpixels,dim_s),dtype=np.int32)
self.gpu_helper.prior_sigma_s = self.params.prior_sigma_s_sum.gpu.copy()
self.gpu_helper.sigma_s_helper = gpuarray.zeros((nSuperpixels,3),dtype=np.int64)
self.gpu_helper.log_count_helper = gpuarray.zeros((nSuperpixels,1),dtype=np.double)
def example(img=None,
tess='I',
eval_cell_idx=True,
eval_v=True,
show_downsampled_pts=True,
valid_outside=True,
base=[1, 1],
scale_spatial=.1,
scale_value=100,
permute_cell_idx_for_display=True,
nLevels=3,
vol_preserve=False,
zero_v_across_bdry=[0, 0],
use_lims_when_plotting=True):
show_downsampled_pts = bool(show_downsampled_pts)
eval_cell_idx = bool(eval_cell_idx)
eval_v = bool(eval_cell_idx)
valid_outside = bool(valid_outside)
permute_cell_idx_for_display = bool(permute_cell_idx_for_display)
vol_preserve = bool(vol_preserve)
if img is None:
img = Img(get_std_test_img())
else:
img = Img(img)
img = img[:, :, ::-1] # bgr2rgb
tw = TransformWrapper(
nRows=img.shape[0],
nCols=img.shape[1],
nLevels=nLevels,
base=base,
scale_spatial=scale_spatial, # controls the prior's smoothness
scale_value=scale_value, # controls the prior's variance
tess=tess,
vol_preserve=vol_preserve,
zero_v_across_bdry=zero_v_across_bdry,
valid_outside=valid_outside)
print tw
# You probably want to do that: padding image border with zeros
border_width = 1
img[:border_width] = 0
img[-border_width:] = 0
img[:, :border_width] = 0
img[:, -border_width:] = 0
# The tw.calc_T_fwd (or tw.calc_T_inv) is always done in gpu.
# After using it to compute new pts,
# you may want to use remap (to warp an image accordingly).
# If you will use tw.remap_fwd (or tw.remap_inv), which is done in gpu,
# then the image type can be either float32 or float64.
# But if you plan to use tw.tw.remap_fwd_opencv (or tw.remap_inv_opencv),
# which is done in cpu (hence slightly lower) but supports better
# interpolation methods, then the image type must be np.float32.
# img_original = CpuGpuArray(img.copy().astype(np.float32))
img_original = CpuGpuArray(img.copy().astype(np.float64))
img_wrapped_fwd = CpuGpuArray.zeros_like(img_original)
img_wrapped_bwd = CpuGpuArray.zeros_like(img_original)
seed = 0
np.random.seed(seed)
ms_Avees = tw.get_zeros_PA_all_levels()
ms_theta = tw.get_zeros_theta_all_levels()
for level in range(tw.ms.nLevels):
if level == 0:
tw.sample_gaussian(level,
ms_Avees[level],
ms_theta[level],
mu=None) # zero mean
else:
tw.sample_from_the_ms_prior_coarse2fine_one_level(ms_Avees,
ms_theta,
level_fine=level)
print('\nimg shape: {}\n'.format(img_original.shape))
# You don't have use these. You can use any 2d array
# that has two columns (regardless of the number of rows).
pts_src = tw.pts_src_dense
# Create buffers for the output
pts_fwd = CpuGpuArray.zeros_like(pts_src)
pts_inv = CpuGpuArray.zeros_like(pts_src)
for level in range(tw.ms.nLevels):
#######################################################################
# instead of the tw.sample_from_the_ms_prior() above,
# you may want to use one of the following.
# 1)
# tw.sample_gaussian(level,ms_Avees[level],ms_theta[level],mu=None)# zero mean
# 2)
# tw.sample_gaussian(level,ms_Avees[level],ms_theta[level],mu=some_user_specified_mu)
# The following should be used only for level>0 :
# 3)
# tw.sample_normal_in_one_level_using_the_coarser_as_mean(Avees_coarse=ms_Avees[level-1],
# Avees_fine=ms_Avees[level],
# theta_fine=ms_theta[level],
# level_fine=level)
#
#######################################################################
# You can also change the values this way:
# cpa_space = tw.ms.L_cpa_space[level]
# theta = cpa_space.get_zeros_theta()
# theta[:] = some values
# Avees = cpa_space.get_zeros_PA()
# cpa_space.theta2Avees(theta,Avees)
# cpa_space.update_pat(Avees)
# This step is important and must be done
# before are trying to "use" the new values of
# the (vectorized) A's.
tw.update_pat_from_Avees(ms_Avees[level], level)
if eval_v:
# Evaluating the velocity field.
# You don't have to do it in unless you want to visualize v.
# (when evaluting the treansformation, v will be internally
# evaluated anyway -- but its result won't be stored)
tw.calc_v(level=level)
# optional, if you want to time it
timer_gpu_T_fwd = GpuTimer()
# Simply calling
# tic = time.clock()
# and then
# tic = time.clock()
# won't work.
# In fact, most likely you will get that toc-tic is zero.
# You need to use the GpuTimer object. When you do that,
# one side effect is that suddenly the toc-tic from above will
# give you a more realistic result.
tic = time.clock()
timer_gpu_T_fwd.tic()
tw.calc_T_fwd(pts_src, pts_fwd, level=level)
timer_gpu_T_fwd.toc()
toc = time.clock()
print 'Time, in sec, for computing T_fwd:'
print timer_gpu_T_fwd.secs
print toc - tic # likely to be 0, unless you also used the GpuTimer.
# You can also time the inv of course. Results will be similar.
tw.calc_T_inv(pts_src, pts_inv, level=level)
if eval_cell_idx:
# cell_idx is computed here just for display.
cell_idx = CpuGpuArray.zeros(len(pts_src), dtype=np.int32)
tw.calc_cell_idx(pts_src,
cell_idx,
level,
permute_for_disp=permute_cell_idx_for_display)
# If may also want ro to time the remap.
# However, the remap is usually very fast (e.g, about 2 milisec).
# timer_gpu_remap_fwd = GpuTimer()
# tic = time.clock()
# timer_gpu_remap_fwd.tic()
# tw.remap_fwd(pts_inv=pts_inv,img=img_original,img_wrapped_fwd=img_wrapped_fwd)
tw.remap_fwd(pts_inv=pts_inv,
img=img_original,
img_wrapped_fwd=img_wrapped_fwd)
# timer_gpu_remap_fwd.toc()
# toc = time.clock()
# If the img type is np.float32, you may also use
# tw.remap_fwd_opencv instead of tw.remap_fw. The differences between
# the two methods are explained above
tw.remap_inv(pts_fwd=pts_fwd,
img=img_original,
img_wrapped_inv=img_wrapped_bwd)
# For display purposes, do gpu2cpu transfer
print("For display purposes, do gpu2cpu transfer")
if eval_cell_idx:
cell_idx.gpu2cpu()
if eval_v:
tw.v_dense.gpu2cpu()
pts_fwd.gpu2cpu()
pts_inv.gpu2cpu()
img_wrapped_fwd.gpu2cpu()
img_wrapped_bwd.gpu2cpu()
figsize = (12, 12)
plt.figure(figsize=figsize)
if eval_v:
plt.subplot(332)
tw.imshow_vx()
plt.title('vx')
plt.subplot(333)
tw.imshow_vy()
plt.title('vy')
if eval_cell_idx:
plt.subplot(331)
cell_idx_disp = cell_idx.cpu.reshape(img.shape[0], -1)
plt.imshow(cell_idx_disp)
plt.title('tess (type {})'.format(tess))
if show_downsampled_pts:
ds = 20
pts_src_grid = pts_src.cpu.reshape(tw.nRows, -1, 2)
pts_src_ds = pts_src_grid[::ds, ::ds].reshape(-1, 2)
pts_fwd_grid = pts_fwd.cpu.reshape(tw.nRows, -1, 2)
pts_fwd_ds = pts_fwd_grid[::ds, ::ds].reshape(-1, 2)
pts_inv_grid = pts_inv.cpu.reshape(tw.nRows, -1, 2)
pts_inv_ds = pts_inv_grid[::ds, ::ds].reshape(-1, 2)
use_lims = use_lims_when_plotting
# return tw
plt.subplot(334)
plt.plot(pts_src_ds[:, 0], pts_src_ds[:, 1], 'r.')
plt.title('pts ds')
tw.config_plt()
plt.subplot(335)
plt.plot(pts_fwd_ds[:, 0], pts_fwd_ds[:, 1], 'g.')
plt.title('fwd(pts)')
tw.config_plt(axis_on_or_off='on', use_lims=use_lims)
plt.subplot(336)
plt.plot(pts_inv_ds[:, 0], pts_inv_ds[:, 1], 'b.')
plt.title('inv(pts)')
tw.config_plt(axis_on_or_off='on', use_lims=use_lims)
plt.subplot(337)
plt.imshow(img_original.cpu.astype(np.uint8))
plt.title('img')
# plt.axis('off')
plt.subplot(338)
plt.imshow(img_wrapped_fwd.cpu.astype(np.uint8))
# plt.axis('off')
plt.title('fwd(img)')
plt.subplot(339)
plt.imshow(img_wrapped_bwd.cpu.astype(np.uint8))
# plt.axis('off')
plt.title('inv(img)')
return tw
